On The Algorithmic and System Interface of BIG LEARNING

Speaker:        Dr. Eric Xing
                School of Computer Science
                Carnegie Mellon University

Title:          "On The Algorithmic and System Interface of BIG LEARNING"

Date:           Thursday, 19 December 2013

Time:           11:00am - 12 noon

Venue:          Room 5619 (near lifts 31 or 32), HKUST

Abstract:

In many modern applications built on massive data and using
high-dimensional models, such as web-scale content extraction via topic
models, genome-wide association mapping via sparse regression, and image
understanding via deep neural network, one needs to handle BIG machine
learning problems that threaten to exceed the limit of current
infrastructures and algorithms. While ML community continues to strive for
new scalable algorithms, and several attempts on developing new system
architectures for BIG ML have emerged to address the challenge on the
backend, good dialogs between ML and system remain difficult --- most
algorithmic research remain disconnected from the real system/data they
are to face; and the generality, programmability, and theoretical
guarantee of most systems on ML programs remain largely unclear. In this
talk, I will present some recent work from the CMU SAILING Lab on big
learning problems in social network, personalized genome medicine, and
computer vision, and demonstrate how innovations in scalable algorithms
and distributed system design work in concert to achieve multiple orders
of magnitude of scalability, with provable guarantee on correctness. I
will introduce a new platform - Petuum -- built on such algorithmic and
system interface aiming at providing a general-purpose distributed
framework for big machine learning.


***************
Biography:

Dr. Eric Xing is an associate professor in the School of Computer Science
at Carnegie Mellon University. His principal research interests lie in the
development of machine learning and statistical methodology; especially
for solving problems involving automated learning, reasoning, and
decision-making in high-dimensional, multimodal, and dynamic possible
worlds in social and biological systems. Professor Xing received a Ph.D.
in Molecular Biology from Rutgers University, and another Ph.D. in
Computer Science from UC Berkeley. His current work involves, 1)
foundations of statistical learning, including theory and algorithms for
estimating time/space varying-coefficient models, sparse structured
input/output models, and nonparametric Bayesian models; 2) computational
and statistical analysis of gene regulation, genetic variation, and
disease associations; and 3) large-scale systems for machine learning.
Professor Xing has published over 190 peer-reviewed papers, and is an
associate editor of the Annals of Applied Statistics (AOAS), the Journal
of American Statistical Association (JASA), the IEEE Transaction of
Pattern Analysis and Machine Intelligence (PAMI), the PLoS Journal of
Computational Biology, and an Action Editor of the Machine Learning
Journal (MLJ), the Journal of Machine Learning Research (JMLR). He is a
member of the DARPA Information Science and Technology (ISAT) Advisory
Group, a recipient of the NSF Career Award, the Sloan Fellowship, the
United States Air Force Young Investigator Award, the IBM Open
Collaborative Research Award, and best paper awards in a number of premier
conferences including UAI, ACL, SDM, and ISMB. He is the Program Chair of
ICML 2014 to take place in Beijing.